consolidate: absorb task_arithmetic__naive

task_arithmetic__naive/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

task_arithmetic__naive/README.md

@@ -0,0 +1,43 @@
+---
+library_name: transformers
+tags: [model-merging, mergeability, training-free, quotient-merge-distance]
+---
+
+# polypythia-14m-s1s2__task_arithmetic__naive
+
+Training-free merged checkpoint from the **Mergeability** sweep
+(`benchmark/emit_lm.py --real`), produced by weight-space merging of two independently
+trained parents. No gradient steps were taken.
+
+| field | value |
+|---|---|
+| pair_id | `polypythia-14m-s1s2` |
+| parent_a | `EleutherAI/pythia-14m-seed1` |
+| parent_b | `EleutherAI/pythia-14m-seed2` |
+| ceiling | `(floor-relative)` |
+| operator | `task_arithmetic` |
+| alignment | `naive` |
+| align_method | `permutation` |
+| regime | `indep_seed` |
+| eval_langs | `eng` |
+| nll_merge | `18.706` |
+| nll_floor | `5.1597` |
+| param_coverage | `1.0` |
+| MS | `None` |
+
+## How it was made
+
+Parents were loaded, activations extracted on a shared calibration corpus, and the merge applied
+either **naive** (parents combined in their own coordinates) or **aligned** (parent B carried into
+parent A's residual-stream basis via `common.alignment.residual_basis_map` before merging —
+permutation for same-width pairs, orthogonal/rectangular for cross-width).
+
+`MS` is the recovery score from `common.eval.mergeability_score` (merged vs. floor vs. ceiling), the
+same normalisation used by Zhou et al., so it is comparable across rows of the sweep.
+
+## Caveats
+
+Sub-1B merges are noisy; an aligned signal where the naive one is noise is the finding, not a bug.
+Rows without a joint ceiling are floor-relative and must not be read as absolute recovery.
+
+Generated automatically — see the [mergeability repo](https://github.com/suchirsalhan/mergeability).

task_arithmetic__naive/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "dtype": "float16",
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": null,
+  "rope_parameters": {
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.14.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

task_arithmetic__naive/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "5.14.1"
+}

task_arithmetic__naive/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5441752f7a1cce2834d1d7aa2a3a983cb404d953f96773368b309806a527e8fd
+size 28143920

task_arithmetic__naive/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<|endoftext|>"
+}